GPT-5.3-Codex-Spark vs Claude Haiku 4.5

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

GPT-5.3-Codex-Spark is clearly ahead on the aggregate, 87 to 62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.3-Codex-Spark's sharpest advantage is in coding, where it averages 82.3 against 41.7. The single biggest benchmark swing on the page is LiveCodeBench, 80 to 36.

GPT-5.3-Codex-Spark is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.80 input / $4.00 output per 1M tokens for Claude Haiku 4.5. That is roughly 2.0x on output cost alone. GPT-5.3-Codex-Spark is the reasoning model in the pair, while Claude Haiku 4.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.3-Codex-Spark gives you the larger context window at 256K, compared with 200K for Claude Haiku 4.5.

Quick Verdict

Pick GPT-5.3-Codex-Spark if you want the stronger benchmark profile. Claude Haiku 4.5 only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

85.6

Claude Haiku 4.5

56.7

90
Terminal-Bench 2.0
53
82
BrowseComp
62
83
OSWorld-Verified
57

Coding

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

82.3

Claude Haiku 4.5

41.7

91
HumanEval
60
80
SWE-bench Verified
48
80
LiveCodeBench
36
85
SWE-bench Pro
46

Multimodal & Grounded

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

88.3

Claude Haiku 4.5

78.4

86
MMMU-Pro
82
91
OfficeQA Pro
74

Reasoning

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92.7

Claude Haiku 4.5

68.9

94
SimpleQA
65
92
MuSR
63
97
BBH
81
91
LongBench v2
72
92
MRCRv2
70

Knowledge

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

78.3

Claude Haiku 4.5

53.6

97
MMLU
68
95
GPQA
67
93
SuperGPQA
65
91
OpenBookQA
63
88
MMLU-Pro
73
42
HLE
11
88
FrontierScience
64

Instruction Following

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

92

Claude Haiku 4.5

86

92
IFEval
86

Multilingual

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

90.8

Claude Haiku 4.5

80.1

94
MGSM
82
89
MMLU-ProX
79

Mathematics

GPT-5.3-Codex-Spark

GPT-5.3-Codex-Spark

96.7

Claude Haiku 4.5

73.3

98
AIME 2023
68
98
AIME 2024
70
97
AIME 2025
69
94
HMMT Feb 2023
64
96
HMMT Feb 2024
66
95
HMMT Feb 2025
65
95
BRUMO 2025
67
98
MATH-500
81

Frequently Asked Questions

Which is better, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark is ahead overall, 87 to 62. The biggest single separator in this matchup is LiveCodeBench, where the scores are 80 and 36.

Which is better for knowledge tasks, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for knowledge tasks in this comparison, averaging 78.3 versus 53.6. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for coding in this comparison, averaging 82.3 versus 41.7. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for math in this comparison, averaging 96.7 versus 73.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for reasoning in this comparison, averaging 92.7 versus 68.9. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for agentic tasks in this comparison, averaging 85.6 versus 56.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for multimodal and grounded tasks in this comparison, averaging 88.3 versus 78.4. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for instruction following in this comparison, averaging 92 versus 86. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.3-Codex-Spark or Claude Haiku 4.5?

GPT-5.3-Codex-Spark has the edge for multilingual tasks in this comparison, averaging 90.8 versus 80.1. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.